WEKO3
アイテム
Disease-gene relations extraction using domain dictionaries and named entity recognition filtering
https://ipsj.ixsq.nii.ac.jp/records/59087
https://ipsj.ixsq.nii.ac.jp/records/590871a0c9199-acc6-44c0-af87-e37b71c0664a
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
Copyright (c) 2005 by the Information Processing Society of Japan
|
|
オープンアクセス |
Item type | SIG Technical Reports(1) | |||||||
---|---|---|---|---|---|---|---|---|
公開日 | 2005-12-22 | |||||||
タイトル | ||||||||
タイトル | Disease-gene relations extraction using domain dictionaries and named entity recognition filtering | |||||||
タイトル | ||||||||
言語 | en | |||||||
タイトル | Disease-gene relations extraction using domain dictionaries and named entity recognition filtering | |||||||
言語 | ||||||||
言語 | eng | |||||||
資源タイプ | ||||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||||
資源タイプ | technical report | |||||||
著者所属 | ||||||||
University of Tokyo | ||||||||
著者所属 | ||||||||
University of Tokyo CREST Japan Science and Technology agency | ||||||||
著者所属 | ||||||||
University of Tokyo CREST Japan Science and Technology agency School of Informatics University of Manchester | ||||||||
著者所属(英) | ||||||||
en | ||||||||
University of Tokyo | ||||||||
著者所属(英) | ||||||||
en | ||||||||
University of Tokyo,CREST Japan Science and Technology agency | ||||||||
著者所属(英) | ||||||||
en | ||||||||
University of Tokyo,CREST Japan Science and Technology agency,School of Informatics University of Manchester | ||||||||
著者名 |
Hong-WooChun
× Hong-WooChun
|
|||||||
著者名(英) |
Hong-Woo, Chun
× Hong-Woo, Chun
|
|||||||
論文抄録 | ||||||||
内容記述タイプ | Other | |||||||
内容記述 | We extracted disease-gene relations from MedLine using disease/gene dictionaries which are constructed from six public DBs. Since dictionary matching produces a large number of false positives we developed a method of machine learning-based named entity recognition (NER) to filter out false recognitions of disease/gene names. We found that the performance of relation extraction depends on the performance of NER filtering and that the filtering improves the precision of relation extraction by 26.7% at the cost of a small reduction in recall. | |||||||
論文抄録(英) | ||||||||
内容記述タイプ | Other | |||||||
内容記述 | We extracted disease-gene relations from MedLine using disease/gene dictionaries which are constructed from six public DBs. Since dictionary matching produces a large number of false positives, we developed a method of machine learning-based named entity recognition (NER) to filter out false recognitions of disease/gene names. We found that the performance of relation extraction depends on the performance of NER filtering and that the filtering improves the precision of relation extraction by 26.7% at the cost of a small reduction in recall. | |||||||
書誌レコードID | ||||||||
収録物識別子タイプ | NCID | |||||||
収録物識別子 | AA12055912 | |||||||
書誌情報 |
情報処理学会研究報告バイオ情報学(BIO) 巻 2005, 号 128(2005-BIO-003), p. 81-87, 発行日 2005-12-22 |
|||||||
Notice | ||||||||
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. | ||||||||
出版者 | ||||||||
言語 | ja | |||||||
出版者 | 情報処理学会 |